I've ran out of ideas

Aaron Glenn aaron.glenn at gmail.com
Thu Nov 18 17:53:05 PST 2004


On Fri, 19 Nov 2004 10:11:59 +1100 (EST),
lukem.freebsd at cse.unsw.edu.au <lukem.freebsd at cse.unsw.edu.au> wrote:
> The simple answer is that both iostat and dd are giving you the correct
> results. Try your dd again with a smaller block size (like the 512 byte
> default) and you should see that disk throughput is closer to what you are
> seeing for your web server.

The /www partition it's reading from was made with -b 65536 and -f 8192.

> I would theorise that your web server is probably only issuing fairly
> small disk reads, so your network performance is being bound by the disk.

That was my first hunch; hence creating a separate partition with
obscene blocksizes (-:

> To test this theory, you could:
> 
> * create an mfs partition and serve off it to see what kind of performance
>    you can get
> * see if you can tweak the web server to use larger reads and writes.
> 
> In your original message you said that increasing the disk block size
> improved performance, which would also indicate that you are being limited
> by disk performance.

I doubt increasing it even more would help. Law of diminishing returns
and all that; then again I'm no expert. Thoughts?

Regards,
aaron.glenn


More information about the freebsd-performance mailing list